DeepAI AI Chat
Log In Sign Up

Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation

07/06/2020
by   Chunnan Wang, et al.
Harbin Institute of Technology
0

The search space of neural architecture search (NAS) for convolutional neural network (CNN) is huge. To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only. Such kind of fixed architecture performs well when enough cells and channels are used. However, when the architecture becomes more lightweight, the performance decreases significantly. To obtain better lightweight architectures, more flexible and diversified neural architectures are in demand, and more efficient methods should be designed for larger search space. Motivated by this, we propose MoARR algorithm, which utilizes the existing research results and historical information to quickly find architectures that are both lightweight and accurate. We use the discovered high-performance cells to construct network architectures. This method increases the network architecture diversity while also reduces the search space of cell structure design. In addition, we designs a novel multi-objective method to effectively analyze the historical evaluation information, so as to efficiently search for the Pareto optimal architectures with high accuracy and small parameter number. Experimental results show that our MoARR can achieve a powerful and lightweight model (with 1.9 which is better than the state-of-the-arts. The explored architecture is transferable to ImageNet and achieves 76.0 parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/14/2018

Evolutionary Neural Architecture Search for Image Restoration

Convolutional neural network (CNN) architectures have traditionally been...
05/25/2019

Dynamic Cell Structure via Recursive-Recurrent Neural Networks

In a recurrent setting, conventional approaches to neural architecture s...
10/06/2022

POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique

Automating the research for the best neural network model is a task that...
01/11/2021

Unchain the Search Space with Hierarchical Differentiable Architecture Search

Differentiable architecture search (DAS) has made great progress in sear...
05/29/2020

DC-NAS: Divide-and-Conquer Neural Architecture Search

Most applications demand high-performance deep neural architectures cost...
03/16/2022

On Redundancy and Diversity in Cell-based Neural Architecture Search

Searching for the architecture cells is a dominant paradigm in NAS. Howe...